MUMBAI, India, July 13 -- Intellectual Property India has published a patent application (202641082119 A) filed by Sr University on July 03, 2026, for An Edge-Intelligent Multimodal Vision System For Real-Time Medicine Tablet Recognition With Context-Aware Natural Language Audio Assistance.
Inventors include Yannam N L Sowjanya Reddy; Johnson Kolluri; and Dr. V. Chandra Shekhar Rao.
The application for the patent was published on July 10, 2026, under issue no. 28/2026.
Abstract: AN EDGE-INTELLIGENT MULTIMODAL VISION SYSTEM FOR REAL-TIME MEDICINE TABLET RECOGNITION WITH CONTEXT-AWARE NATURAL LANGUAGE AUDIO ASSISTANCE An edge-intelligent multimodal vision system and corresponding framework are disclosed for real-time medicine tablet recognition coupled with context-aware natural language audio assistance. The system features an onboard optical sensor that captures an image of a solid oral dosage form, which is subsequently processed entirely on a localized edge computing device. The edge device utilizes an optimized deep learning pipeline to concurrently extract multiple physical features, including shape, color, dimensions, texture, and surface imprints, matching them against a localized database to identify the medicine without cloud intervention. Once identified, a natural language generation engine combines the medicine's identity with personalized patient profiles and schedules from an internal database to generate context-specific instructions. These instructions are converted into natural language audio output via an integrated audio subsystem, providing real-time, privacy- preserving, and accessible medication guidance to elderly or visually impaired users.
Disclaimer: Curated by HT Syndication.
